© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 34008
    Prev
    Next
    INDEX
    Explanations

    commands, times, and replies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    landa
    -0.09
     ########.
    -0.09
    aukee
    -0.08
    972
    -0.08
    .wp
    -0.08
     tôn
    -0.08
    ¦æĥħ
    -0.08
    ¶Į
    -0.08
     deflate
    -0.07
    boom
    -0.07
    POSITIVE LOGITS
    ael
    0.10
    och
    0.10
    .scalablytyped
    0.10
     typings
    0.08
    emen
    0.07
     ?,
    0.07
    INavigation
    0.07
     inconvenient
    0.07
    &t
    0.07
    0.07
    Activations Density 0.097%

    No Known Activations